arXiv cs.LG
· Papers
Regularity-Aware Stochastic MGDA with Adaptive Conflict-Avoidant Update Direction Control
arXiv:2607.15412v1 Announce Type: new Abstract: Multi-objective learning (MOL) aims to optimize multiple objectives simultaneously. The multi-gradient descent algorithm (MGDA) is a workhorse that iteratively updates along a common descent or conflict-avoidant (CA) direction across objectives. In stochastic settings, ho